Fairness and Bias in Online Selection

Jose Correa · Andres Cristi · Paul Duetting · Ashkan Norouzi-Fard


Keywords: [ Algorithms ] [ Online Learning Algorithms ]

[ Abstract ]
[ Slides
[ Paper ]
[ Visit Poster at Spot A5 in Virtual World ] [ Visit Poster at Spot B0 in Virtual World ]
Wed 21 Jul 9 a.m. PDT — 11 a.m. PDT
Spotlight presentation: Online Learning 1
Wed 21 Jul 6 a.m. PDT — 7 a.m. PDT


There is growing awareness and concern about fairness in machine learning and algorithm design. This is particularly true in online selection problems where decisions are often biased, for example, when assessing credit risks or hiring staff. We address the issues of fairness and bias in online selection by introducing multi-color versions of the classic secretary and prophet problem. Interestingly, existing algorithms for these problems are either very unfair or very inefficient, so we develop optimal fair algorithms for these new problems and provide tight bounds on their competitiveness. We validate our theoretical findings on real-world data.

Chat is not available.